design-template-swiss-minimalist
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to analyze and integrate design templates into a user's existing codebase, which acts as an ingestion point for untrusted data. This surface could be exploited if malicious instructions are embedded in the project files.
- Ingestion points: The agent is instructed to "Review the current component architecture" and "Identify the tech stack" by reading files in the user's project (using
Read,Glob, andGreptools). - Boundary markers: The skill does not provide delimiters or instructions for the agent to ignore commands that might be embedded in the analyzed code.
- Capability inventory: The skill uses
WriteandEdittools to modify the user's project files based on its analysis. - Sanitization: No specific validation or sanitization steps are defined for the code content before it is processed or modified.
Audit Metadata